引導式測驗 · 中等 等級

對抗性例子和穩健性測驗

測試您對對抗性範例、攻擊者知識、威脅模型、訓練防禦和範圍穩健性評估的理解。

相關引導路徑對抗性例子和穩健性
問題 1 的 8

Under a specified threat model, what is an adversarial example?

預覽每個問題8 問題

當您參加測驗時,就會出現答案和解釋。

  1. Under a specified threat model, what is an adversarial example?
    • An input crafted to cause a model error using changes allowed by that threat model
    • Any ordinary prediction error on unmodified input
    • An input that must contain tiny, imperceptible pixel changes
    • A model update that improves accuracy on every distribution
  2. 「白盒」攻擊與「黑盒」攻擊有何不同?
    • 白盒攻擊僅適用於白色影像
    • 在白盒中,攻擊者可以存取模型的內部/梯度;在黑盒中,僅輸出
    • 黑盒攻擊總是更快
    • 白盒攻擊不需要計算
  3. FGSM(快速梯度符號法)透過...製作了一個對抗性範例
    • 隨機打亂像素
    • 從頭開始重新訓練模型
    • 相對於輸入,沿著損失梯度的符號方向邁出一步
    • 裁切影像
  4. What is adversarial training commonly used for?
    • Guaranteeing robustness to every possible attack
    • Proving a classifier is fair
    • Eliminating all clean-data errors
    • Improving robustness against the adversarial threat model represented during training
  5. 為什麼對抗性例子的「可轉移性」值得關注?
    • 針對一種模型的攻擊通常會愚弄其他模型,從而實現黑盒攻擊
    • 它使模型訓練速度變慢
    • 它增加了儲存成本
    • 它僅影響音訊模型
  6. How are prompt-injection attacks related to image adversarial examples?
    • They are identical bounded pixel perturbations
    • Both exploit model vulnerabilities, but prompt injection has a distinct instruction and system threat model
    • Prompt injection requires changing model weights
    • Image adversarial examples only affect text prompts
  7. Why must an adversarial-robustness report specify the perturbation norm and budget?
    • They determine the model’s number of parameters
    • They guarantee transfer to every attack
    • They define which input changes the reported robustness claim covers
    • They replace the need to state an attacker’s access
  8. Which pair of measures helps distinguish clean performance from performance under a specified attack?
    • Training-set size and GPU memory
    • Tokenization rate and context length
    • Model file size and parameter dtype
    • Clean accuracy and robust accuracy under the stated attack setting